Training in progress, epoch 3

logs/events.out.tfevents.1702267900.joseph_legion.22340.15

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8abd9b6dab9832c0d3f92fbdd6e3a04c699eafcacdf00ddb8d04a1d9f3c2fd5a
-size 5404
+oid sha256:e8bec381b9e192f5ed4d3cb22e79a602f08d4f1d2aa0f4e1b5ae292433a619f3
+size 5884

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b346f9a604944be9d0766f923a39024f08d03e88258336da81cd5f7b176af4d
+oid sha256:55437ed52f425242d1c865d80635ab093a2b2b73916952b9ace75c6df6bc8603
 size 44692608

run-2/checkpoint-591/config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "google/bert_uncased_L-4_H-256_A-4",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 256,
+  "id2label": {
+    "0": 0,
+    "1": 1
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "label2id": {
+    "0": 0,
+    "1": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 4,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-2/checkpoint-591/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55437ed52f425242d1c865d80635ab093a2b2b73916952b9ace75c6df6bc8603
+size 44692608

run-2/checkpoint-591/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4026fb3e478ffb5e42cc3bde4a193ae278cb8c1513fdc8de2c72fa0b87ff28a6
+size 89430010

run-2/checkpoint-591/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70141f0acfe75a3d2817bbed9f14bb13efceb08fee84dae3818267566941c957
+size 14308

run-2/checkpoint-591/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af02e55f498539def209d4b27c06ad0b1603f296a0074bef071099950f494758
+size 1064

run-2/checkpoint-591/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

run-2/checkpoint-591/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-2/checkpoint-591/trainer_state.json

@@ -0,0 +1,70 @@
+{
+  "best_metric": 0.7488882712618121,
+  "best_model_checkpoint": "tinybert-TG-HS-HX-parentpretrained\\run-2\\checkpoint-591",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 591,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.6784454644765522e-06,
+      "loss": 0.564,
+      "step": 197
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6989994441356309,
+      "eval_loss": 0.5322139859199524,
+      "eval_runtime": 125.0015,
+      "eval_samples_per_second": 57.567,
+      "eval_steps_per_second": 0.456,
+      "step": 197
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.258834098357414e-06,
+      "loss": 0.5261,
+      "step": 394
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7388827126181212,
+      "eval_loss": 0.496852844953537,
+      "eval_runtime": 124.8189,
+      "eval_samples_per_second": 57.652,
+      "eval_steps_per_second": 0.457,
+      "step": 394
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 8.392227322382761e-07,
+      "loss": 0.5052,
+      "step": 591
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7488882712618121,
+      "eval_loss": 0.48156076669692993,
+      "eval_runtime": 124.658,
+      "eval_samples_per_second": 57.726,
+      "eval_steps_per_second": 0.457,
+      "step": 591
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 985,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 133009215775884.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.8786599620319323,
+    "learning_rate": 2.09805683059569e-06,
+    "num_train_epochs": 5,
+    "temperature": 9
+  }
+}

run-2/checkpoint-591/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c03531167986b5590a04d8bd7d50baf3ca6f53132698a5ba9216e4386d4bf3c
+size 4792